检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Kuhrmann, Marco Diebold, Philipp MacDonell, Stephen Münch, Jürgen Department of Computer Science Institute for Applied Software Systems Engineering Clausthal University of Technology Goslar Germany Fraunhofer IESE Kaiserslautern Germany Auckland University of Technology Auckland New Zealand Reutlingen University Bögblingen Germany

software and system development is complex and diverse, and a multitude of development approaches is used and combined with each other to address the manifold challenges companies face today. To study the current state of the practice and to build a sound understanding about the utility of different development approaches and their application to modern software system development, in 2016, we launched the HELENA initiative. This paper introduces the 2nd HELENA workshop and provides an overview of the current project state. In the workshop, six teams present initial findings from their regions, impulse talk are given, and further steps of the HELENA roadmap are discussed. Copyright © 2021, The Authors. All rights reserved.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

A Novel DRAM-Based Process-in-Memory Architecture and its Implementation for CNNs

A Novel DRAM-Based Process-in-Memory Architecture and its Im...

引用

Asia and South Pacific Design Automation Conference

作者： Chirag Sudarshan Taha Soliman Cecilia De la Parra Christian Weis Leonardo Ecco Matthias Jung Norbert Wehn Andre Guntoro Microelectronic Systems Design Research Group TU Kaiserslautern Kaiserslautern Germany Corporate Research (CR/ADT2) Robert Bosch GmbH – Stuttgart Germany Fraunhofer Institute for Experimental Software Engineering (IESE) Kaiserslautern Germany

ISBN: (数字)9781450379991

ISBN: (纸本)9781728180571

Processing-in-Memory (PIM) is an emerging approach to bridge the memory-computation gap. One of the key challenges of PIM architectures in the scope of neural network inference is the deployment of traditional area-intensive arithmetic multipliers in memory technology, especially for DRAM-based PIM architectures. Hence, existing DRAM PIM architectures are either confined to binary networks or exploit the analog property of the sub-array bitlines to perform bulk bit-wise logic operations. The former reduces the accuracy of predictions, i.e. Quality-of-results, while the latter increases overall latency and power *** this paper, we present a novel DRAM-based PIM architecture and implementation for multi-bit-precision CNN inference. The proposed implementation relies on shifter based approximate multiplications specially designed to fit into commodity DRAM architectures and its technology. The main goal of this work is to propose an architecture that is fully compatible with commodity DRAM architecture and to maintain a similar thermal design power (i.e. < 1W ). Our evaluation shows that the proposed DRAM-based PIM has a small area overhead of 6.6% when compared with an 8 Gb commodity DRAM. Moreover, the architecture delivers a peak performance of 8.192 TOPS per memory channel while maintaining a very high energy efficiency. Finally, our evaluation also shows that the use of approximate multipliers results in a negligible drop in prediction-accuracy (i.e. < 2 %) in comparison with conventional CNN inference that relies on traditional arithmetic multipliers.

关键词： Performance evaluation Training Quantization (signal) Neural networks Random access memory Transforms Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Getting Ready for the European Health Data Space (Ehds): The Iderha's Plan to Align with the Ehds Requirements for the Secondary Use of Health Data

SSRN

引用

SSRN 2024年

作者： Hussein, Rada Balaur, Irina Burmann, Anja Ćwiek-Kupczyńska, Hanna Gadiya, Yojana Ghosh, Soumyabrata Jayathissa, Prabath Katsch, Florian Kremer, Andreas Lähteenmäki, Jaakko Meng, Zhaoling Morasek, Kathrin Rancourt, Rebecca C. Satagopam, Venkata Sauermann, Stefan Scheider, Simon Stamm, Tanja A. Muehlendyck, Christian Gribbon, Philip Ludwig Boltzmann Institute for Digital Health and Prevention Salzburg Austria Luxembourg Centre for Systems Biology University of Luxembourg Luxembourg Fraunhofer Institute for Software and Systems Engineering Dortmund Germany Discovery Research Screening Port Hamburg Germany Theodor Stern Kai 7 Frankfurt60590 Germany Bonn-Aachen International Center for Information Technology University of Bonn Bonn Germany Center for Medical Data Science Medical University of Vienna Vienna Austria ITTM S.A. Luxembourg VTT Technical Research Centre of Finland Ltd Espoo Finland Clinical Modeling and Evidence Integration Sanofi CambridgeMA United States Institute of Outcomes Research Center for Medical Data Science Medical University of Vienna Austria Ludwig Boltzmann Institute for Arthritis and Rehabilitation Vienna Austria Medical School Berlin Berlin Germany Faculty Life Science Engineering FH Technikum Wien Vienna Austria TU Dortmund Dortmund Germany Johnson & Johnson Medical GmbH Norderstedt Germany

Objective: The European Health Data Space (EHDS) shapes the digital transformation of healthcare in Europe. The EHDS regulations will also accelerate the use of health data for research, innovation, policy-making, and regulatory activities for secondary use of data (known as EHDS2). The Integration of heterogeneous Data and Evidence towards Regulatory and HTA Acceptance (IDERHA) project builds one of the first pan-European health data spaces in alignment with the EHDS2 requirements, addressing lung cancer as a *** and Methods: In this study, we conducted a comprehensive review of the EHDS regulations and technical requirements for EHDS2. Mainly utilizing the results of the Joint Action Towards the European Health Data Space (TEHDAS) project to identify the framework of IDERHA’s alignment with EHDS. We also conducted an internal webinar and an external workshop with EHDS experts to share expertise on the EHDS requirements and ***: We identified the minimum-set of requirements for aligning IDERHA infrastructure with the planned EHDS regulations, including user journey, concepts, terminologies, and standards. The future IDERHA framework (i.e., platform architecture, standardization approaches, documentation, etc.) will be developed ***: The IDERHA's alignment plan with EHDS2 necessitates the implementation of three categories of standardization for: data discoverability (DCAT-AP), enabling semantics interoperability (OMOP), and health data exchange (DICOM and FHIR). The main challenge is that some standards are still being refined, e.g., the extension of the DCAT-AP (HealthDCAT-AP). Additionally, extensions to the OHDSI OMOP CMD for representing the Patient-Generated Health Data are still needed. Finally, proper mapping between standards (FHIR/OMOP) is a prerequisite for proper data ***: Collaboration, sharing lessons learned, and creating synergy among the current EHDS initiatives and projects are critical

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

Patient Adoption of Digital Use Cases in Family Medicine and a Nuanced Implementation Approach for Family Doctors: Quantitative Web-Based Survey Study

引用

JMIR Formative Research 2025年 9卷 e58867页

作者： Beerbaum, Julian Robens, Sibylle Fehring, Leonard Mortsiefer, Achim Meister, Sven Health Care Informatics Faculty of Health School of Medicine Witten/Herdecke University Witten Germany Department of Psychology and Psychotherapy Witten/Herdecke University Witten Germany Department of Gastroenterology Helios University Hospital Wuppertal Witten/Herdecke University Wuppertal Germany Faculty of Health School of Medicine Witten/Herdecke University Witten Germany General Practice II and Patient-Centeredness in Primary Care Institute of General Practice and Primary Care Faculty of Health School of Medicine Witten/Herdecke University Witten Germany Department Healthcare Fraunhofer Institute for Software and Systems Engineering Dortmund Germany

Background: Digital use cases describe the application of technology to achieve specific outcomes. Several studies in health care have examined patients’ overall attitudes toward digitalization and specific use cases. However, these studies have failed to provide a comparison of patient acceptance criteria between inherently different digital use cases in family medicine. Objective: To address this research gap, this paper aimed to assist family doctors in selecting digital use cases by comparing the underlying patient adoption factors and in driving usage of these use cases by presenting a differentiated implementation approach. Methods: Adapting an established Unified Theory of Acceptance and Use of Technology (UTAUT) questionnaire to 4 digital use cases in family medicine, we surveyed a large cross-sectional sample of adults living in Germany. The results of the web-based survey were then analyzed via descriptive statistics, ANOVA, and hierarchical regression models to compare the effects of sociodemographic and technology acceptance factors on the intention to use a specific use case. Results: Our web-based survey included 1880 participants. Of these 1880 participants, only 304 (16.2%) agreed that the degree of digitalization is important when selecting a family practice. However, more digitally literate participants attributed greater importance to this criterion (B=0.226, SE 0.023;β=.223;P<.001), and digital literacy was found to be dependent on age (Welch F_3,968.29=53.441;P<.001). Regarding sociodemographic characteristics, only digital literacy demonstrated a significant effect on the intention to use for all use cases, particularly scheduling doctor appointments online (B=0.322, SE 0.033;β=.408;P<.001). Furthermore, performance expectancy was the strongest predictor of the intention to use for all use cases, while further effects of technology acceptance factors depended on the use case (receiving medical consultations via video: B=0.603, SE 0.04

关键词： digital anamnesis digital health eHealth electronic health records family doctor online appointment scheduling technology acceptance UTAUT video consultation

来源：评论

学校读者我要写书评

暂无评论

BODYTUNE: Multi Auscultation Device-Personal Health Parameter Monitoring at Home

引用

Current Directions in Biomedical engineering 2021年第2期7卷 5-8页

作者： Salvi, Rutuja Fuentealba, Patricio Henze, Jasmin Burmann, Anja Spiller, Moritz Hellwig, Stefan Faldemolaei, Niki Boese, Axel Illanes, Alfredo Friebe, Michael IDTM GmbH Recklinghausen Germany IDTM GmbH Recklinghausen Germany Instituto de Electricidad y Electrónica Facultad de Ciencias de la Ingeniería Universidad Austral de Chile Valdivia Chile Fraunhofer Institute for Software and Systems Engineering Dortmund Germany HealthTec Innovation Laboratory Surgical Audio Guidance Otto-von-Guericke-University Magdeburg Germany ExoEconomy San Diego United States HealthTec Innovation Laboratory Otto-von-Guericke-University Magdeburg Germany MEDICS GmbH Magdeburg Germany HealthTec Innovation Laboratory Otto-von-Guericke-University Magdeburg Germany

Auscultation methods allow the non-invasive diagnosis of pathological conditions (e.g., of the lung, heart or blood vessels) based on sounds that the body produces (e.g., breathing, heartbeat, swallowing or the blood flow). Through regular homebased examinations and Big Data combined with Machine learning techniques like Deep Learning, these could help detect diseases in an early stage, thus preventing serious health conditions and subsequently ensuring optimal therapy through continuous monitoring. This paper presents BODYTUNE, a novel inexpensive multi-Auscultation system that aims at providing a tool for establishing a baseline of audio signal derived classification parameters that could be used for the self-monitoring of personal health for everybody through the analysis of deviations from that baseline. In the future, Big Data analysis could additionally lead to prediction and early detection of disease events. © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Spectrum analysis

来源：评论

学校读者我要写书评

暂无评论

An Efficient Soft Error Tolerant Approach to Enhance Reliability of TCAM

An Efficient Soft Error Tolerant Approach to Enhance Reliabi...

引用

International Conference on Advances in Science, engineering and Robotics Technology

作者： Rumana Afrin Muhammad Sheikh Sadi Jan Jurjens Department of Computer Science & Engineering Khulna University of Engineering & Techonology Department of Computer Science University of Koblenz-Landau and Fraunhofer-Institute for Software and Systems Engineering ISST

ISBN: (纸本)9781728134468

Ternary Content Addressable Memory (TCAM) is a kind of extraordinary memory which is used to search operations in routers, firewalls, network address translators, and entire content in a single clock cycle. It is a special kind of memory which is used in highly reliable network applications. These systems require high reliability since a single error may interrupt any computation which may cause total system failure. However, TCAM is facing serious reliability challenges due to soft errors. The probability of soft errors in TCAM is increasing progressively due to alpha-particle, cosmic rays, high-vitality particles, and ionizing impacts of barometrical neutron. In order to minimize the risks of soft errors in TCAM, a new idea is proposed in this paper where the search key is constructed in a tricky way and the contents of the TCAM are ordered in a sequential pattern. The proposed method provides soft error tolerance with a low data overhead. Experimental study shows how the proposed method outperforms the existing method to tolerate soft error.

关键词： Soft errors Ternary content addressable memory (TCAM) Memory reliability Error correction code Don't care bits Telecommunications Access Method search key Error correction codes clock cycle Web address network applications system failures Routers

来源：评论

学校读者我要写书评

暂无评论

A C Code Generator for Fast Inference and Simple Deployment of Convolutional Neural Networks on Resource Constrained systems

A C Code Generator for Fast Inference and Simple Deployment ...

引用

IOT, Electronics and Mechatronics Conference (IEMTRONICS), IEEE International

作者： Oliver Urbann Simon Camphausen Arne Moos Ingmar Schwarz Sören Kerner Maximilian Otten Automation and Embedded Systems Fraunhofer IML Dortmund Germany Robotics Research Institute TU Dortmund University Dortmund Germany Software and Information Engineering Fraunhofer IML Dortmund Germany

ISBN: (数字)9781728196152

ISBN: (纸本)9781728196169

Inference of Convolutional Neural Networks in time critical applications usually requires a GPU. In robotics or embedded devices these are often not available due to energy, space and cost constraints. Furthermore, installation of a deep learning framework or even a native compiler on the target platform is not possible. This paper presents a neural network code generator (NNCG) that generates from a trained CNN a plain ANSI C code file that encapsulates the inference in single a function. It can easily be included in existing projects and due to lack of dependencies, cross compilation is usually possible. Additionally, the code generation is optimized based on the known trained CNN and target platform following four design principles. The system is evaluated utilizing small CNN designed for this application. Compared to TensorFlow XLA and Glow speed-ups of up to 11.81 can be shown and even GPUs are outperformed regarding latency.

关键词： Robots Artificial neural networks Machine learning Libraries Generators Embedded systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Carotid Sound Signal Artifact Detection based on Discrete Wavelet Transform Decomposition

引用

Current Directions in Biomedical engineering 2021年第2期7卷 299-302页

作者： Fuentealba, Patricio Salvi, Rutuja Henze, Jasmin Burmann, Anja Boese, Axel Ataide, Elmer Spiller, Moritz Illanes, Alfredo Friebe, Michael IDTM GmbH Recklinghausen Germany Instituto de Electricidad y Electrónica Facultad de Ciencias de la Ingeniería Universidad Austral de Chile Valdivia Chile Fraunhofer Institute for Software and Systems Engineering Dortmund Germany HealthTec Innovation Laboratory Otto-von-Guericke-University + MEDICS GmbH Magdeburg Germany Division of Nuclear Medicine Department of Radiology + INKA Application Driven Research Innovation Laboratory Otto-von-Guericke University Magdeburg Germany HealthTec Innovation Laboratory Surgical Audio Guidance Otto-von-Guericke-University Magdeburg Germany HealthTec Innovation Laboratory Otto-von- Guericke-University Magdeburg + IDTM GmbH Recklinghausen Germany

Auscultation methods allow a non-invasive diagnosis of cardiovascular diseases like atherosclerosis based on blood flow sounds of the carotid arteries. Since this process is highly dependent on the clinician's experience, it is of great interest to develop automated data processing techniques for objective assessment. We have recently proposed a computerassisted auscultation system that we use to acquire carotid blood flow sounds. In this work, we present an approach for detecting artifacts within the blood flow sound caused by swallowing or coughing events. For this purpose, we first decompose the signal using a discrete wavelet transform (DTW). Then, we compute an energy ratio between the DWT scales associated with the signal information with and without artifacts using a sliding window of 1 s length. Evaluation based on Kruskal-Wallis and Wilcoxon rank-sum tests shows a statistically significant difference (p-value © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A conceptual model of benchmarking data and its implications for data mapping in the data economy

A conceptual model of benchmarking data and its implications...

引用

Multikonferenz Wirtschaftsinformatik, MKWI 2018 - Multiconference on Business Informatics, MKWI 2018

作者： Spiekermann, Markus Wenzel, Sven Otto, Boris Fraunhofer Institute for Software and Systems Engineering ISST Dortmund Germany TU Dortmund Net Order Management Dortmund Germany

ISBN: (纸本)9783935786720

Digitalization of the economy requires enterprises from all industries to revisit their current business models and prepare their organizations for the digital age. One task is the (re-)design of hybrid and digital products and services. The foundation builds the improved interchangeability of data and the availability of external data sources through data markets and platforms. This leads to the requirement of a structured decision-making while mapping data sources to digital products. In order to successfully transform their business and develop valuable new products, companies require methodological help. This paper proposes a high-level conceptual model for the assessment of data sources value. It consists of an approach for comparing data sources based on a common description of data and individual metrics definition enable a benchmark process. The development of the model and its practicability has been validated in a case study with an industrial partner. © 2018 Leuphana Universitat Luneburg. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Schedule Instability in Production Networks: An empirical Study on Drivers and Mechanisms within the Automotive Industry

引用

IFAC-PapersOnLine 2018年第11期51卷 1071-1076页

作者： Moetz, A. Meinlschmidt, J. Otto, B. Volkswagen AG Wolfsburg Germany Technical University Dortmund Germany Fraunhofer Institute for Software and Systems Engineering Germany

Schedule instability in production networks is a highly relevant topic for practitioners and academics lacking research, especially from a network perspective. This paper addresses the phenomenon schedule instability in automotive production networks via an abductive case study approach. The objective of this paper is to • Present a structure of the different drivers influencing schedule instability • Present a model of the different mechanisms to tackle these instabilities • Derive the interdependencies between instability drivers and mechanisms © 2018

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：